AI runtimepackages/ai/knowledge-rag

knowledge-rag package

Retrieval-augmented generation pipeline — chunk, embed, store, retrieve, rerank — pluggable per vector store.

Open docs

Stability: Stable
Scope: Global
Boundary: packages/ai/knowledge-rag
Owners: @nebutra/ai

User query

Retrieval pipeline

Embed queryvector · dim 1536
12ms
Search corpus5 / 12,401 chunks
84ms
Re-ranktop 3 surfaced
22ms

Retrieved chunks3 of 5

To rotate keys, generate a new key, deploy, then revoke the previous secret.

docs/security/api-keys.md142 tokens

Relevance

x

94%

Programmatic rotation can be scheduled via the /v1/keys/rotate endpoint.

docs/api/keys-endpoint.md96 tokens

Relevance

x

88%

Audit logs capture every key create/revoke event for SOC 2 compliance.

docs/security/audit-log.md128 tokens

Relevance

x

71%

12,401 chunks · 1,536-dim local embeddings · 118ms end-to-end

Usagerag.ts

typescript

rag.ts

1import { createKnowledgeBase } from "@nebutra/knowledge-rag";
2
3const kb = createKnowledgeBase({
4  tenantId: org.id,
5  chunkSize: 800,
6  overlap: 120,
7});
8
9await kb.ingest({ docs: await loadDocs() });
10
11const hits = await kb.search("How do I rotate API keys?", { topK: 5 });
12const context = hits.map((h) => h.text).join("\n---\n");

knowledge-rag packagepackage

knowledge-rag package